30 likes | 133 Views
EE122 Project. High Level Description. Goal. To use an interactive network simulation environment that allows students to how end-to-end and network control mechanisms affect various measures of latency and loss How do AIMD protocols perform? Compare various marking-based feedback schemes
E N D
EE122 Project High Level Description
Goal • To use an interactive network simulation environment that allows students to how end-to-end and network control mechanisms affect various measures of latency and loss • How do AIMD protocols perform? • Compare various marking-based feedback schemes • Quantify the role of routing • Quantify the effects of WFQ schedulers • Understand how delay due to admission control can be traded off against network delay
Approach: Sequence of steps that systematically explores the design space • Assume FCFS scheduling, no packet marking but TCP runs on the end hosts • Does TCP behave as advertised? • What is the relationship between network utilization and delay • Change the routes – how does performance change? • Implement a few different kinds of marking schemes (Jean to fill in here) • What is the tangible effect of each scheme (must measure) • What is the complexity of each scheme? (from code) • Implement priority based virtual queues • Assume no marking, but implement WFQ/PGPS at the nodes. Set equal weights. • Add a marking scheme to the scheduling • Assume that the sources are applications which have different rates. Change the WFQ weights to be proportional to these rates. • The flow control scheme may delay packets before admitting them. Assume some Poisson and some CBR sources. When this delay is added to the network delay, how do 1-5 perform? Does anything change?